[ELF] - Dedupliсate FDEs when sections are ICFed.

[grimar]

Summary

When LLD do ICF for 2 identical sections it leaves 2 duplicate entries in .eh_frame
pointing to the same address. After that it fixes .eh_frame_header's header,
so that it says it contains single FDE, though section itself contains 2
(it contains garbage data at tail).

As a result excessive entries in .eh_frame and excessive dummy data in .eh_frame_header
emited to output. Patch fixes that. This is PR34518.

[grimar]

Ping.

[ruiu]

ELF/SyntheticSections.cpp

453–455

// FDEs for garbage-collected or merged-by-ICF sections are dead.

454–457

This code looks odd. The following code is more natural.

if (auto *D = dyn_cast<DefinedRegular>(&B))
  if (auto *Sec = cast_or_null<InputSectionBase>(D->Section))
    return Sec &&  ...;
return false;

[grimar]

• Addressed review comments.

[ruiu]

LGTM

ELF/SyntheticSections.cpp

456

You can remove Sec &&.

ELF/SyntheticSections.cpp

bool EhFrameSection<ELFT>::isFdeLive(EhSectionPiece &Fde,
   // ld.gold with -r. ld.gold may discard only functions and leave their
   // corresponding FDEs, which results in creating bad .eh_frame sections.
   // To deal with that, we ignore such FDEs.
   if (FirstRelI == (unsigned)-1)
     return false;
 
   const RelTy &Rel = Rels[FirstRelI];
   SymbolBody &B = Sec->template getFile<ELFT>()->getRelocTargetSym(Rel);
+
+  // FDEs for garbage-collected or merged-by-ICF sections are dead.
   if (auto *D = dyn_cast<DefinedRegular>(&B))
-    if (D->Section)
-      return cast<InputSectionBase>(D->Section)->Repl->Live;
+    if (auto *Sec = cast_or_null<InputSectionBase>(D->Section))
+      return Sec && Sec->Live && (Sec == Sec->Repl);
   return false;
 }
 
 // .eh_frame is a sequence of CIE or FDE records. In general, there
 // is one CIE record per input object file which is followed by
 // a list of FDEs. This function searches an existing CIE or create a new
 // one and associates FDEs to the CIE.
 template <class ELFT>
 template <class RelTy>

test/ELF/eh-frame-hdr-icf-fde.s

+# REQUIRES: x86
+
+## Testcase checks that we correctly deduplicate FDEs when ICF
+## merges two sections.
+
+# RUN: llvm-mc -filetype=obj -triple=x86_64-unknown-linux %s -o %t
+# RUN: ld.lld %t -o %t2 --icf=all --eh-frame-hdr
+# RUN: llvm-readobj -r %t | FileCheck %s --check-prefix=OBJ
+# RUN: llvm-readobj -s -section-data %t2 | FileCheck %s
+
+# OBJ:      Relocations [
+# OBJ-NEXT:   Section {{.*}} .rela.eh_frame {
+# OBJ-NEXT:     0x20 R_X86_64_PC32 .text.f1 0x0
+# OBJ-NEXT:     0x34 R_X86_64_PC32 .text.f1 0x2
+# OBJ-NEXT:     0x48 R_X86_64_PC32 .text.f2 0x0
+# OBJ-NEXT:     0x5C R_X86_64_PC32 .text.f2 0x2
+# OBJ-NEXT:   }
+# OBJ-NEXT: ]
+
+# CHECK:      Section {
+# CHECK:        Index: 1
+# CHECK:        Name: .eh_frame_hdr
+# CHECK-NEXT:   Type: SHT_PROGBITS
+# CHECK-NEXT:   Flags [
+# CHECK-NEXT:     SHF_ALLOC
+# CHECK-NEXT:   ]
+# CHECK-NEXT:   Address: 0x200158
+# CHECK-NEXT:   Offset: 0x158
+# CHECK-NEXT:   Size: 28
+# CHECK-NEXT:   Link: 0
+# CHECK-NEXT:   Info: 0
+# CHECK-NEXT:   AddressAlignment:
+# CHECK-NEXT:   EntrySize: 0
+# CHECK-NEXT:   SectionData (
+# CHECK-NEXT:     0000: 011B033B 1C000000 02000000 A80E0000
+##                               ^        ^-- FDE(1) PC
+##                               ^-- Number of FDEs
+# CHECK-NEXT:     0010: 38000000 AA0E0000 50000000
+##                               ^-- FDE(2) PC
+# CHECK-NEXT:   )
+# CHECK-NEXT: }
+## FDE(1) == 0x201000 - .eh_frame_hdr(0x200158) = 0xEA8
+## FDE(2) == 0x201000 - .eh_frame_hdr(0x200158) + 2(relocation addend) = 0xEAA
+
+## Check .eh_frame contains CIE and two FDEs remaining after ICF.
+# CHECK-NEXT: Section {
+# CHECK-NEXT:   Index: 2
+# CHECK-NEXT:   Name: .eh_frame
+# CHECK-NEXT:   Type: SHT_PROGBITS
+# CHECK-NEXT:   Flags [
+# CHECK-NEXT:     SHF_ALLOC
+# CHECK-NEXT:   ]
+# CHECK-NEXT:   Address: 0x200178
+# CHECK-NEXT:   Offset: 0x178
+# CHECK-NEXT:   Size: 72
+# CHECK-NEXT:   Link: 0
+# CHECK-NEXT:   Info: 0
+# CHECK-NEXT:   AddressAlignment: 8
+# CHECK-NEXT:   EntrySize: 0
+# CHECK-NEXT:   SectionData (
+# CHECK-NEXT:     0000: 14000000 00000000 017A5200 01781001
+# CHECK-NEXT:     0010: 1B0C0708 90010000 14000000 1C000000
+# CHECK-NEXT:     0020: 680E0000 01000000 00000000 00000000
+# CHECK-NEXT:     0030: 14000000 34000000 520E0000 01000000
+# CHECK-NEXT:     0040: 00000000 00000000
+# CHECK-NEXT:   )
+# CHECK-NEXT: }
+
+# CHECK:     Section {
+# CHECK:       Index:
+# CHECK:       Name: .text
+# CHECK-NEXT:  Type: SHT_PROGBITS
+# CHECK-NEXT:  Flags [
+# CHECK-NEXT:    SHF_ALLOC
+# CHECK-NEXT:    SHF_EXECINSTR
+# CHECK-NEXT:  ]
+# CHECK-NEXT:  Address: 0x201000
+
+.section .text.f1, "ax"
+.cfi_startproc
+nop
+.cfi_endproc
+nop
+.cfi_startproc
+ret
+.cfi_endproc
+
+.section .text.f2, "ax"
+.cfi_startproc
+nop
+.cfi_endproc
+nop
+.cfi_startproc
+ret
+.cfi_endproc

test/ELF/eh-frame-hdr-icf.s

 # REQUIRES: x86
 
 # RUN: llvm-mc -filetype=obj -triple=x86_64-unknown-linux %s -o %t
 # RUN: ld.lld %t -o %t2 --icf=all --eh-frame-hdr
-# RUN: llvm-objdump -s %t2 | FileCheck %s
+# RUN: llvm-objdump -s -section-headers %t2 | FileCheck %s
+
+## Check .eh_frame_hdr contains single FDE and no garbage data at tail.
+# CHECK: Sections:
+# CHECK: Idx Name          Size
+# CHECK:     .eh_frame_hdr 00000014
 
 # CHECK: Contents of section .eh_frame_hdr:
-# CHECK-NEXT: 200158 011b033b 1c000000 01000000 a80e0000
+# CHECK-NEXT: 200158 011b033b 14000000 01000000
 #                                      ^ FDE count
-# CHECK-NEXT: 200168 38000000 00000000 00000000
-#                    ^ FDE for f2
 
-.globl _start, f1, f2
-_start:
-  ret
+.globl f1, f2
 
 .section .text.f1, "ax"
 f1:
   .cfi_startproc
   ret
   .cfi_endproc
 
 .section .text.f2, "ax"
 f2:
   .cfi_startproc
   ret
   .cfi_endproc